BIM: an open ontology for the annotation of biomedical images

Ahmad C. Bukhari, Mate Levente Nagy, Michael Krauthammer, Paolo Ciccarese, Christopher J. O. Baker
2015 International Conference on Biomedical Ontology  
Biomedical images published within the scientific literature play a central role in reporting and facilitating life science discoveries. Existing ontologies and vocabularies describing biomedical imag-es, particularly sequence images, do not provide sufficient seman-tic representation for image annotations generated automatically and/or semi--automatically. We present an open ontology for the annotation of biomedical images (BIM) scripted in OWL/RDF. The BIM ontology provides semantic
more » ... es to describe the manually curated image annotations as well as annotations gener-ated by online bioinformatics services using content extracted from images by the Semantic Enrichment of Biomedical Images (SEBI) system. The BIM ontology is represented in three parts; (i) image vocabularies --which holds vocabularies for the annotation of an image and/or region of interests (ROI) inside an image, as well as vocabularies to represent the pre and post processing states of an image, (ii) text entities --covers annotations from the text that are associated with an image (e.g. image captions) and provides semantic representation for NLP algorithm outputs, (iii) a provenance model -- that contributes towards the maintenance of annotation versioning. To illustrate the BIM ontology's utility, we provide three annotation cases generated by BIM in conjunction with the SEBI image annotation engine. THE BIM ONTOLOGY To better understand the context where BIM is relevant we briefly describe SEBI (semantic enrichment of biomedical images). SEBI is a solution for image annotation
dblp:conf/icbo/BukhariNKCB15 fatcat:kfrvqdncxrhtlonwbt4jbjslu4